Traditionally, database systems have been evaluated in isolation on the basis of standardized benchmarks (e.g., Wisconsin, TPC-C, TPC-D). We argue that very often such a performance analysis does not reflect the actual use of the DBMSs in the “real world.” End users typically don't access a stand-alone database system; rather they use a comprehensive application system, in which the database system constitutes an integrated component. In order to derive performance evaluations of practical relevance to the end users, the application system including the database system has to be benchmarked. In this paper, we present TPC-D benchmark results carried out using the SAP R/3 system, an integrated business administration system. Like many other application systems SAP R/3 is based on a commercial relational database system. We compare the SAP R/3 benchmark results with TPC-D results of an isolated database system, the database product that served as SAP R/3's back-end.